MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection.
Hou-I LiuChristine WuJen-Hao ChengWenhao ChaiShian-Yun WangGaowen LiuJenq-Neng HwangHong-Han ShuaiWen-Huang ChengPublished in: CoRR (2024)
Keyphrases
- d objects
- pose estimation
- object recognition
- viewpoint
- multiple views
- multi view
- object detection
- three dimensional
- shape descriptors
- range data
- detection method
- line drawings
- pose normalization
- control points
- cad models
- image sequences
- computer vision
- object classes
- partial matching
- d mesh
- real world objects
- physically plausible
- recognition and pose estimation